Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks

TL;DR

This paper introduces a meta-deep reinforcement learning method combining DQNs and MAML to optimize UAV trajectories for minimizing age-of-information and power in IoT networks, demonstrating faster convergence and adaptability.

Contribution

It presents a novel meta-RL approach integrating DQNs with MAML for scalable, efficient UAV data collection optimization under varying objectives.

Findings

Faster convergence compared to traditional RL methods.

Effective adaptation to different AoI and power objectives.

Achieves lower AoI and power consumption overall.

Abstract

Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle(UAV) that collects data. Our aim is to optimize the UAV flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.